Downloads · 30 days
11
3% of all-time downloads
Qwen2.5-0.5B-GSM8K-SFT
tripathysagar/Qwen2.5-0.5B-GSM8K-SFT
Qwen2.5-0.5B-GSM8K-SFT is a machine learning model from tripathysagar. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuned Qwen/Qwen2.5-0.5B on GSM8K for math reasoning with a structured answer format.
All-time downloads
377
Public
Parameters
494M
3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors988 MB · 99%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Feb 23, 2026
- Updated
- Mar 11, 2026
- SHA
- 1e64df6a
Base models
Datasets
Model card
From the Hugging Face model README
Qwen2.5-0.5B-GSM8K-SFT
Fine-tuned Qwen/Qwen2.5-0.5B on GSM8K for math reasoning with a structured answer format.
Training Details
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen2.5-0.5B |
| Method | SFT + LoRA |
| LoRA r / alpha | 32 / 16 |
| LoRA targets | all-linear |
| Epochs | 1 |
| Learning rate | 0.0002 |
| Batch size | 8 × 4 (grad accum) |
| Training examples | 1024 |
| Precision | bf16 |
Answer Format
The model is trained to end responses with:
The answer is: {number}.
System Prompt
You are a helpful math assistant. Solve the problem step by step, then give your final answer as a single number on the last line in exact format
The answer is: {number}.
- Type
- qwen2
- Created
- Feb 23, 2026
- Updated
- Mar 11, 2026